From 0c6d0acdf3b93eee221a3093ce22c0c76b0b2127 Mon Sep 17 00:00:00 2001 From: Matěj Cepl Date: Fri, 30 Nov 2018 11:35:50 +0100 Subject: Initial version --- epubgrep.py | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) create mode 100755 epubgrep.py diff --git a/epubgrep.py b/epubgrep.py new file mode 100755 index 0000000..e3051bf --- /dev/null +++ b/epubgrep.py @@ -0,0 +1,54 @@ +#!/usr/bin/env python3 +import argparse +import os.path +import re +import zipfile + +from typing import Any, Dict, List, Optional, Tuple + +import epub_meta + +parser = argparse.ArgumentParser(description='Grep through EPub book') +parser.add_argument('pattern') +parser.add_argument('filename') +parser.add_argument('-i', '--ignore-case', + action='store_true', + help="make search case insensitive") +args = parser.parse_args() + +search_flags = 0 +if args.ignore_case: + search_flags |= re.I + + +def get_chapter_title(mdata:List[Dict[str, Any]], fname:str) -> Optional[Tuple[str, int]]: + found_list = [(x['title'], x['index']) for x in mdata if x['src'] == fname] + if len(found_list) > 0: + chap_title = found_list[0][0].strip(' \t.0123456789') + return chap_title, found_list[0][1] + else: + return ('Unknown', 0) + + +def grep_book(filename:str, pattern:str, flags): + sought_RE = re.compile(pattern, flags) + + metadata = epub_meta.get_epub_metadata(filename) + book = zipfile.ZipFile(filename) + + for zif in book.infolist(): + with book.open(zif) as inf: + printed_title = False + for line in inf: + decoded_line = line.decode() + if sought_RE.search(decoded_line): + if not printed_title: + chap_info = get_chapter_title(metadata.toc, + zif.filename) + print("{}. {}:\n".format(chap_info[1], chap_info[0])) + printed_title = True + print(decoded_line) + +assert os.path.isfile(args.filename), "{} is not EPub file.".format(args.filename) +book_fname = os.path.realpath(args.filename) +grep_book(book_fname, args.pattern, search_flags) -- cgit